© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98270
    Prev
    Next
    INDEX
    Explanations

    words ending in -le

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires most strongly on tokens that are numeric sequences (multi‐digit numbers or numeral tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ゼント
    -0.79
    splitContainer
    -0.73
    PyErr
    -0.73
    쵸
    -0.73
    mensagem
    -0.71
    ActionPerformed
    -0.70
     hermes
    -0.70
    letterSpacing
    -0.70
    PackageInfo
    -0.70
    ازه
    -0.69
    POSITIVE LOGITS
     rubble
    1.14
     cattle
    1.09
     mingle
    1.00
     Pringle
    0.99
     gravel
    0.96
    istle
    0.95
     Cattle
    0.93
     steeple
    0.93
    stable
    0.93
     Sparkle
    0.91
    Activations Density 0.058%

    No Known Activations